library(tidyverse)
library(sf)

# Required packages
library(pacman)

p_load(char = c(
  # Visualizations
  "showtext", "ggtext", "ggsankey", "patchwork",
  
  # Data Loading
  "haven", "readxl",
  
  # GIS
  "tmaptools", "rmapshaper", "sf",
  
  # Good 'ol Tidyverse
  "tidyverse"
  
))

# Loading CSV data
dataFrame <- read.csv("data.csv")

# Creating a new variable
dataFrame$age_square <- age^2

# Subsetting the data frame
dataFrame <- dataFrame[dataFrame$age_square >= 250, ]

# Merging
merge(dataFrame, aux_data, by = "id")

# Loading CSV data
dataFrame <- read_csv("data.csv")

# Creating a variable, subsetting and merging:
dataFrame <- dataFrame %>%
  mutate(age_square = age^2) %>%
  filter(age_square >= 250) %>%
  left_join(aux_data, by = "id")

# Loading CSV data
import delimited "data.csv", clear

# Creating a new variable
gen age^2

# Subsetting the data frame
keep if age_square >= 250

# Merging
merge 1:1 id using "aux_data"

# Collapsing data
collapse (mean) age_square, by(country)

# Loading CSV data
dataFrame <- read_csv("data.csv")

# Manipulating data 
dataFrame_new <- dataFrame %>%     # Saving as a different object
  mutate(age_square = age^2) %>%
  filter(age_square >= 250) %>%
  left_join(aux_data, by = "id") %>%
  group_by(country) %>%
  summarise(age_square = mean(age_square))

# Loading libraries
library(pacman)
p_load(readxl, 
       tidyverse, 
       factoextra, 
       cluster, 
       NbClust, 
       FactoMineR, 
       dendextend)

# Loading data base with all the scores

master_data.df <- read_csv("Data/master_data.csv") %>%
  mutate(region4labels = str_replace_all(region, "&", "&\n"))

factors_data <- master_data.df %>%
    select(year, country, starts_with("fct"), roli_index) %>% 
  filter(year == 2015 | year == 2022) %>% # This is the period that we are studying
  dplyr::rename(factor_1 = fct1,
                factor_2 = fct2,
                factor_3 = fct3,
                factor_4 = fct4,
                factor_5 = fct5,
                factor_6 = fct6,
                factor_7 = fct7,
                factor_8 = fct8) %>% # We reshape the data base to make easier the estimations of the rates
  pivot_wider(id_cols = country, names_from = year, 
              values_from = c(factor_1, factor_2, factor_3, factor_4, factor_5, 
                              factor_6, factor_7, factor_8, roli_index,
                              )) %>% # We estimate the rate changes between 2015 and 2022 per factor
  mutate(differences_factor_1 = ((factor_1_2022 - factor_1_2015)/factor_1_2015), 
         differences_factor_2 = ((factor_2_2022 - factor_2_2015)/factor_2_2015),
         differences_factor_3 = ((factor_3_2022 - factor_3_2015)/factor_3_2015),
         differences_factor_4 = ((factor_4_2022 - factor_4_2015)/factor_4_2015),
         differences_factor_5 = ((factor_5_2022 - factor_5_2015)/factor_5_2015),
         differences_factor_6 = ((factor_6_2022 - factor_6_2015)/factor_6_2015),
         differences_factor_7 = ((factor_7_2022 - factor_7_2015)/factor_7_2015),
         differences_factor_8 = ((factor_8_2022 - factor_8_2015)/factor_8_2015),
         differences_roli = (roli_index_2022 - roli_index_2015)/roli_index_2015) %>%
  select(country, starts_with("differences"))

fviz_nbclust(cluster_data, kmeans, method = 'wss') # According to the graph the main change 
                                                   # is produced after the third cluster
fviz_nbclust(cluster_data, kmeans, method = 'silhouette') # According to this method the optimal 
                                                          # number of cluster is two

res2 <- hcut(cluster_data, k = 3, stand = T, hc_metric = 'euclidean') # We use the package FactoMineR